DSpace Collection:

Impact of Virtual Farm Tours on Agrotourism Destination Choice in Sri Lanka

2026-08-04T07:26:06Z

Title: Impact of Virtual Farm Tours on Agrotourism Destination Choice in Sri Lanka Authors: Ariyarathna, S.M.S.L.; Adikaram, W.A.M.K.; Samarawansha, M.G.L.N.K. Abstract: In the Tourism industry, agrotourism has gained more attention as a form of sustainable tourism and this helps to rural development, culture heritage preservation, enhancing the tourist knowledge about agricultural lifestyle. Sri Lanka can provide opportunities for tourists to engage with tea plantations, spice gardens, organic farms, and traditional rural communities. Potential tourist can experience farm environments before making travel decisions by using virtual farm tours, including video-based tours and interactive digital content. Limited research has explored how virtual farm tours shaping agrotourism destination selection. This study uses a quantitative approach with 300 agrotourism-interested respondents selected through purposive sampling. Data were collected via an online questionnaire after viewing a virtual farm tour video. Measures used a five-point Likert scale, and data were analyzed using SPSS (Version 26) with reliability, validity, and moderate analysis. Pearson correlation analysis revealed a moderate positive relationship between virtual farm tours and agrotourism destination selection (r = .459, p < .01), and between trust and destination selection (r = .364, p < .01). A strong positive relationship was found between trust and virtual farm tours (r = .752, p < .01). Moderation analysis further indicated that trust significantly strengthens the relationship between virtual farm tours and destination selection (β = .098, p = .017), explaining additional variance (R² = .007), confirming its moderating role. This study, based on the Stimulus–Organism–Response (S-O-R) framework, finds that virtual farm tours significantly influence agrotourism destination selection in Sri Lanka, with trust strengthening this relationship. The results highlight the importance of authentic virtual content. Tourism stakeholders should invest in realistic, highquality virtual tours to enhance trust and attract global tourists.

AI-Based Tea Leaf Disease Detection Using Deep Learning and Image Recognition

2026-08-04T06:42:11Z

Title: AI-Based Tea Leaf Disease Detection Using Deep Learning and Image Recognition Authors: Kaushica, J.K.; Sudharshan, V. Abstract: Tea (Camellia sinensis) is one of the most economically important plantation crops in Sri Lanka; however, foliar diseases such as blister blight and brown blight continue to cause significant yield and quality losses if not identified at early stages. Conventional disease detection methods rely heavily on manual visual inspection, which is time-consuming, subjective, and difficult to scale across large plantation areas. To address these limitations, this study proposes a deep learning–based tea leaf disease detection system using image recognition and a custom Convolutional Neural Network (CNN), with an emphasis on real-time field applicability. A dataset of 1,200 tea leaf images was collected from tea estates in the upcountry region of Sri Lanka under natural field conditions. The dataset comprises three classes: healthy leaves, blister blight–infected leaves, and brown blight–infected leaves. Images were preprocessed using resizing, normalization, and data augmentation techniques to enhance robustness against lighting variations and background noise. The CNN model was trained and evaluated using a 70:15:15 train–validation–test split. Experimental evaluation demonstrates that the proposed model achieves an overall classification accuracy of 92.4% and an F1-score of 0.92, indicating effective discrimination among disease classes. The trained model was successfully integrated into an Android-based mobile application, enabling ondevice inference with an average prediction time of less than two seconds per image, making it suitable for real-time agricultural use without continuous internet connectivity. Despite promising results, the study is limited by the moderate dataset size and variability in lighting conditions during image acquisition. Future work will focus on dataset expansion, improved robustness under diverse field environments, and large-scale field validation. The proposed system highlights the potential of deep learning–enabled mobile solutions to support precision agriculture and early disease management in Sri Lanka’s tea industry.

Determinants of Knowledge, Attitudes, and Behaviours toward Aflatoxin Contamination: A Structural Equation Modelling Approach in Sri Lanka

2026-08-04T06:34:20Z

Title: Determinants of Knowledge, Attitudes, and Behaviours toward Aflatoxin Contamination: A Structural Equation Modelling Approach in Sri Lanka Authors: Shashini, W.V.N.; Sarap, G.M.S.; Peiris, T.U.S.; Ranawana, V.; Chandrasekara, G.A.P. Abstract: Aflatoxin contamination in food products is an emerging public health concern in Sri Lanka due to its carcinogenic and hepatotoxic effects. There is limited research on consumer knowledge, attitudes, and behaviours (KAB) regarding aflatoxin prevention, among Sri Lankan housewives. This study assessed the KAB of Sri Lankan housewives regarding aflatoxin contamination and examined the relationships among these constructs using Structural Equation Modelling (SEM). A cross-sectional study was conducted from November 2024 to February 2025 among 397 Sri Lankan housewives aged ≥18 years selected through voluntary convenience sampling using community flyers and social media platforms. Data were collected using a pre-tested intervieweradministered telephone questionnaire covering socio-demographic characteristics and KAB related to aflatoxin contamination. Ethical procedures were followed and informed consent was obtained from all participants. Data were analyzed using SPSS 26.0 and AMOS 23.0. Knowledge levels were categorized based on percentage scores. Confirmatory Factor Analysis (CFA) and SEM were used to validate constructs and examine relationships among KAB variables. Knowledge showed good reliability (Cronbach’s α = 0.850), while attitudes demonstrated excellent reliability (α = 0.992). Behaviour reliability was comparatively low (α = 0.483). SEM revealed a strong positive association between knowledge and attitudes (β = 0.732, p < 0.001) and a weak but significant association between knowledge and behaviours (β = 0.181, p = 0.042). However, attitudes were not significantly associated with behaviours (β = −0.030, p = 0.727). Education level significantly predicted both knowledge and attitudes (p < 0.001). Overall knowledge levels were low (48.9%) despite relatively positive attitudes and behaviours. These findings suggest that improving aflatoxinrelated knowledge may support safer food practices among Sri Lankan housewives. However, findings should be interpreted cautiously due to the cross-sectional design, moderate model fit, and potential response bias associated with telephone-based surveys.

Halal Food Consumption Behavior among Muslim Consumers in Sri Lanka

2026-08-04T06:27:51Z

Title: Halal Food Consumption Behavior among Muslim Consumers in Sri Lanka Authors: Perera, M.K.B; Sasanka, U.B.E; Weerasinghe, P.K.K.H.; Umanga, U.D. Abstract: This research examines the factors influencing halal food purchasing decisions among Muslim consumers in Sri Lanka. The research applies the Theory of Planned Behavior as the theoretical framework and examines the effects of Religious Commitment, Trust in Halal Certification, Perceived Product Quality, and Social Influence on halal food consumption behavior. This study is particularly relevant given the expansion of the global halal market and the existing knowledge gap concerning consumer behavior in the Sri Lankan context. A cross-sectional quantitative research design was used, and data were collected from 300 Muslim consumers through a structured online survey using a convenience sampling technique. The instrument was adapted from previously validated scales, and reliability and validity were confirmed prior to analysis. Descriptive statistics, reliability analysis, Pearson correlation, and multiple linear regression were applied to analyze the data. The findings showed strong reliability, with Cronbach’s alpha values exceeding 0.70 for all constructs and an overall reliability coefficient of 0.912. The regression model accounted for 58% of the variance in halal food consumption behavior. The strongest predictors were Religious Commitment (β = 0.351, p < 0.001) and Trust in Halal Certification (β = 0.285, p < 0.001). Perceived Product Quality was also a significant predictor (β = 0.152, p = 0.013), but Social Influence did not reach statistical significance (β = 0.105, p = 0.083). The findings indicate that halal purchasing decisions among Muslim consumers are driven by religious commitment, confidence in halal certification authorities, and perceptions of product quality. These results imply that manufacturers and certifying bodies should ensure religious compliance, prioritize product quality in line with the Tayyib concept, and implement transparent digital verification systems to strengthen consumer trust. Future research may explore the moderating effects of age and Perceived Behavioral Control through longitudinal studies.